{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:D5REZQ3F75RZRYMKNZLRO6OA4X","short_pith_number":"pith:D5REZQ3F","schema_version":"1.0","canonical_sha256":"1f624cc365ff6398e18a6e571779c0e5d4d201a925974eb8a686ae5e769028e2","source":{"kind":"arxiv","id":"2401.03407","version":7},"attestation_state":"computed","paper":{"title":"Bilateral Reference for High-Resolution Dichotomous Image Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dehong Gao, Deng-Ping Fan, Jorma Laaksonen, Li Liu, Nicu Sebe, Peng Zheng, Wanli Ouyang","submitted_at":"2024-01-07T07:56:47Z","abstract_excerpt":"We introduce a novel bilateral reference framework (BiRefNet) for high-resolution dichotomous image segmentation (DIS). It comprises two essential components: the localization module (LM) and the reconstruction module (RM) with our proposed bilateral reference (BiRef). The LM aids in object localization using global semantic information. Within the RM, we utilize BiRef for the reconstruction process, where hierarchical patches of images provide the source reference and gradient maps serve as the target reference. These components collaborate to generate the final predicted maps. We also introd"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2401.03407","kind":"arxiv","version":7},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-07T07:56:47Z","cross_cats_sorted":[],"title_canon_sha256":"aab99c8c78eea2323c42e7f8b6c54c90ce05a2d22254b5f1cc0d61df76aaeea9","abstract_canon_sha256":"002812231573614f62789b813a917090eaca666796c412bad99f3acff3a8d51e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:43:05.672660Z","signature_b64":"S0xCrAiBZwgp+Y8Xm5QxM6kCKSDhJWeHN7PQIPBj51PZGAPtU2dHsGeEEk9+ncCwMvt3PaWVJDJh/xRX1fvVCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1f624cc365ff6398e18a6e571779c0e5d4d201a925974eb8a686ae5e769028e2","last_reissued_at":"2026-07-05T11:43:05.672153Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:43:05.672153Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bilateral Reference for High-Resolution Dichotomous Image Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dehong Gao, Deng-Ping Fan, Jorma Laaksonen, Li Liu, Nicu Sebe, Peng Zheng, Wanli Ouyang","submitted_at":"2024-01-07T07:56:47Z","abstract_excerpt":"We introduce a novel bilateral reference framework (BiRefNet) for high-resolution dichotomous image segmentation (DIS). It comprises two essential components: the localization module (LM) and the reconstruction module (RM) with our proposed bilateral reference (BiRef). The LM aids in object localization using global semantic information. Within the RM, we utilize BiRef for the reconstruction process, where hierarchical patches of images provide the source reference and gradient maps serve as the target reference. These components collaborate to generate the final predicted maps. We also introd"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.03407","kind":"arxiv","version":7},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2401.03407/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2401.03407","created_at":"2026-07-05T11:43:05.672211+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.03407v7","created_at":"2026-07-05T11:43:05.672211+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.03407","created_at":"2026-07-05T11:43:05.672211+00:00"},{"alias_kind":"pith_short_12","alias_value":"D5REZQ3F75RZ","created_at":"2026-07-05T11:43:05.672211+00:00"},{"alias_kind":"pith_short_16","alias_value":"D5REZQ3F75RZRYMK","created_at":"2026-07-05T11:43:05.672211+00:00"},{"alias_kind":"pith_short_8","alias_value":"D5REZQ3F","created_at":"2026-07-05T11:43:05.672211+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24361","citing_title":"SignNet-1M: Large-Scale Multilingual Sign Language Video Dataset with Downstream Benchmarks","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14552","citing_title":"LiWi: Layering in the Wild","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14552","citing_title":"LiWi: Layering in the Wild","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2603.01993","citing_title":"Cultivating Forensic Reasoning for Generalizable Multimodal Manipulation Detection","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14552","citing_title":"LiWi: Layering in the Wild","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00401","citing_title":"SIMON: Saliency-aware Integrative Multi-view Object-centric Neural Decoding","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27958","citing_title":"TripVVT: A Large-Scale Triplet Dataset and a Coarse-Mask Baseline for In-the-Wild Video Virtual Try-On","ref_index":54,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/D5REZQ3F75RZRYMKNZLRO6OA4X","json":"https://pith.science/pith/D5REZQ3F75RZRYMKNZLRO6OA4X.json","graph_json":"https://pith.science/api/pith-number/D5REZQ3F75RZRYMKNZLRO6OA4X/graph.json","events_json":"https://pith.science/api/pith-number/D5REZQ3F75RZRYMKNZLRO6OA4X/events.json","paper":"https://pith.science/paper/D5REZQ3F"},"agent_actions":{"view_html":"https://pith.science/pith/D5REZQ3F75RZRYMKNZLRO6OA4X","download_json":"https://pith.science/pith/D5REZQ3F75RZRYMKNZLRO6OA4X.json","view_paper":"https://pith.science/paper/D5REZQ3F","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.03407&json=true","fetch_graph":"https://pith.science/api/pith-number/D5REZQ3F75RZRYMKNZLRO6OA4X/graph.json","fetch_events":"https://pith.science/api/pith-number/D5REZQ3F75RZRYMKNZLRO6OA4X/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/D5REZQ3F75RZRYMKNZLRO6OA4X/action/timestamp_anchor","attest_storage":"https://pith.science/pith/D5REZQ3F75RZRYMKNZLRO6OA4X/action/storage_attestation","attest_author":"https://pith.science/pith/D5REZQ3F75RZRYMKNZLRO6OA4X/action/author_attestation","sign_citation":"https://pith.science/pith/D5REZQ3F75RZRYMKNZLRO6OA4X/action/citation_signature","submit_replication":"https://pith.science/pith/D5REZQ3F75RZRYMKNZLRO6OA4X/action/replication_record"}},"created_at":"2026-07-05T11:43:05.672211+00:00","updated_at":"2026-07-05T11:43:05.672211+00:00"}